Constraining Nuclear Weak Interactions in Astrophysics and New Many-Core Algorithms for Neuroevolutio

Weak interactions involving atomic nuclei are critical components in a broad range of as- trophysical phenomenon. As allowed Gamow-Teller transitions are the primary path through which weak interactions in nuclei operate in astrophysical contexts, the constraint of these nuclear transitions is an important goal of nuclear astrophysics.;In this work, the charged current nuclear weak interaction known as electron capture is studied in the context of stellar core-collapse supernovae (CCSNe). Specifically, the sensitivity of the core-collapse and early post-bounce phases of CCSNe to nuclear electron capture rates are examined. Electron capture rates are adjusted by factors consistent with uncer- tainties indicated by comparing theoretical rates to those deduced from charge-exchange and beta-decay measurements. With the aide of such sensitivity studies, the diverse role of electron capture on thousands of nuclear species is constrained to a few tens of nuclei near N ~ 50 and A ~ 80 which dictate the primary response of CCSNe to nuclear electron capture. As electron capture is shown to be a leading order uncertainty during the core-collapse phase of CCSNe, future experimental and theoretical efforts should seek to constrain the rates of nuclei in this region.;Furthermore, neutral current neutrino-nuclear interactions in the tens-of-MeV energy range are important in a variety of astrophysical environments including core-collapse super- novae as well as in the synthesis of some of the solar systems rarest elements. Estimates for inelastic neutrino scattering on nuclei are also important for neutrino detector construction aimed at the detection of astrophysical neutrinos. Due to the small cross sections involved, direct measurements are rare and have only been performed on a few nuclei. For this rea- son, indirect measurements provide a unique opportunity to constrain the nuclear transition strength needed to infer inelastic neutrino-nucleus cross sections. Herein the (6Li, 6Li&feet;) inelastic scattering reaction at 100 MeV/u is shown to indirectly select the relevant transitions for inelastic neutrino-nucleus scattering. Specifically, the probes unique selectivity of isovector- spin transfer excitations (Delta S = 1, DeltaT = 1, DeltaTz = 0) is demonstrated, thereby allowing the extraction of Gamow-Teller transition strength in the inelastic channel.;Finally, the development and performance of a newly established technique for the sub- field of artificial intelligence known as neuroevolution is described. While separate from the physics that is discussed, these algorithmic advancements seek to improve the adoption of machine learning in the scientific domain by enabling neuroevolution to take advantage of modern heterogeneous compute architectures. Because the evolution of neural network pop- ulations offloads the choice of specific details about the neural networks to an evolutionary search algorithm, neuroevolution can increase the accessibility of machine learning. However, the evolution of neural networks through parameter and structural space presents a novel di- vergence problem when mapping the evaluation of these networks to many-core architectures. The principal focus of the algorithm optimizations described herein are on improving the feed-forward evaluation time when tens-to-hundreds of thousands of heterogeneous neural networks are evaluated concurrently.